Skip to content

fix: support Opus/OGG output format #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
derspotter wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: support Opus/OGG output format #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions cmd/speak.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -535,6 +535,8 @@ func inferFormatFromExt(path string) string {
return "mp3_44100_128"
case ".wav", ".wave":
return "pcm_44100"
case ".ogg", ".opus":
return "opus_48000_64"
default:
return ""
}
Expand Down
18 changes: 14 additions & 4 deletions internal/elevenlabs/client.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,11 +213,15 @@ func (c *Client) StreamTTS(ctx context.Context, voiceID string, payload TTSReque
return nil, err
}
u.Path = path.Join(u.Path, "/v1/text-to-speech", voiceID, "stream")
q := u.Query()
if latency > 0 {
q := u.Query()
q.Set("optimize_streaming_latency", fmt.Sprint(latency))
u.RawQuery = q.Encode()
}
if payload.OutputFormat != "" {
q.Set("output_format", payload.OutputFormat)
payload.OutputFormat = "" // don't send in body
}
u.RawQuery = q.Encode()

bodyBytes, err := json.Marshal(payload)
if err != nil {
Expand All @@ -229,7 +233,7 @@ func (c *Client) StreamTTS(ctx context.Context, voiceID string, payload TTSReque
return nil, err
}
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Accept", "audio/mpeg")
req.Header.Set("Accept", "*/*")
req.Header.Set("xi-api-key", c.apiKey)

resp, err := c.httpClient.Do(req)
Expand All @@ -253,6 +257,12 @@ func (c *Client) ConvertTTS(ctx context.Context, voiceID string, payload TTSRequ
return nil, err
}
u.Path = path.Join(u.Path, "/v1/text-to-speech", voiceID)
q := u.Query()
if payload.OutputFormat != "" {
q.Set("output_format", payload.OutputFormat)
payload.OutputFormat = ""
}
u.RawQuery = q.Encode()

bodyBytes, err := json.Marshal(payload)
if err != nil {
Expand All @@ -264,7 +274,7 @@ func (c *Client) ConvertTTS(ctx context.Context, voiceID string, payload TTSRequ
return nil, err
}
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Accept", "audio/mpeg")
req.Header.Set("Accept", "*/*")
req.Header.Set("xi-api-key", c.apiKey)

resp, err := c.httpClient.Do(req)
Expand Down